Whisper-tiny-es Open-Source Speech Recognition Model - Free Deployment for Precise Recognition of Spanish Speech

Home

Whisper Tiny Es

Developed by arpagon

A speech recognition model fine-tuned on Spanish dataset based on OpenAI Whisper-tiny

Speech Recognition

Transformers

SpanishOpen Source License:Apache-2.0 #Spanish speech recognition #Low-resource optimization #Fine-tuned Whisper

Downloads 26

Release Time : 12/9/2022

Model Overview

This model is a Spanish fine-tuned version of Whisper-tiny, specifically designed for Spanish speech recognition tasks, achieving a 21.4% word error rate on the Common Voice 11.0 Spanish test set.

Model Features

Spanish optimization

Specially fine-tuned for Spanish speech, outperforming the original Whisper-tiny in Spanish recognition

Lightweight model

Based on Whisper-tiny architecture, maintaining a small model size while providing decent recognition accuracy

Open-source license

Released under Apache 2.0 license, allowing both commercial and research use

Model Capabilities

Spanish speech recognition

Speech-to-text

Use Cases

Speech transcription

Spanish meeting minutes

Automatically transcribe Spanish meeting recordings into text records

Word error rate around 21.4%

Voice assistant

Used as speech recognition component for Spanish voice assistant applications

Training Loss	Epoch	Step	Validation Loss	Wer
0.5354	2.01	1000	0.5196	25.5587
0.3328	4.01	2000	0.4889	24.5940
0.4702	6.02	3000	0.4589	22.8354
0.2854	8.02	4000	0.4451	21.6198
0.3537	10.03	5000	0.4412	21.4074

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Whisper Tiny Es

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Whisper tiny Spanish

🚀 Quick Start

✨ Features

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License